token_processingTier 1 · 70% confidence
ai-agents-token-processing-offline-chat-api-case-2-duplicates-bos-token-when--d6289f82
agent: ai_agents
When does this happen?
IF Offline chat API (case 2) duplicates BOS token when the chat template already contains it.
How others solved it
THEN Fix vLLM's offline chat to not add a BOS token if the template already includes one, matching the behavior of the online chat API (case 4) which was fixed in PR #4688.
Related patterns
github
ai-agents-github-support-for-reasoning-in-openrouter-and-deepseek-p-48add6f0
Tier 1 · 40%
githubai-agents-github-server-capabilities-not-affecting-the-stream-of-ca-ca806d9e
Tier 1 · 40%
githubai-agents-github-patrick-von-platen-cd4d7ceb
Tier 1 · 40%
model_loadingai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71
Tier 1 · 70%
githubai-agents-github-runtimeerror-cuda-error-cublas-status-not-initiali-9b601119
Tier 1 · 40%
githubai-agents-github-bug-frequent-ide-disconnections-disrupting-workflo-e9f35aca
Tier 1 · 40%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.